mesh-hq/ragdoll-mcp-server
If you are the rightful owner of ragdoll-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol (MCP) server for Ragdoll AI knowledge base queries.
Ragdoll AI MCP Server
A Model Context Protocol (MCP) server for Ragdoll AI knowledge base queries.
Overview
This MCP server provides a simple interface to query Ragdoll AI knowledge bases through the Model Context Protocol. It allows seamless integration with various LLM client applications including Cursor, Windsurf, and Cline.
Prerequisites
- Bun runtime (v1.2.1 or later)
- Ragdoll AI API key
- Ragdoll AI knowledge base ID
Installation
Clone the repository and install dependencies:
git clone <repository-url>
cd mcp-ragdoll-server
bun install
Configuration
Set up your environment variables:
export RAGDOLL_API_KEY="your-ragdoll-api-key"
export RAGDOLL_KNOWLEDGE_BASE_ID="your-knowledge-base-id"
For persistent configuration, add these to your .bashrc, .zshrc, or create a .env file in the project root.
Running the Server
Start the server:
bun run index.ts
Client Setup
NPX Installation (Recommended)
The simplest way to use this server is via NPX:
npx -y ragdoll-mcp-server
Cursor
To install the Ragdoll MCP server in Cursor IDE:
- Open Cursor IDE
- Go to Settings > Extensions > AI Settings
- Create a file named
mcp.jsonwith the following configuration:
{
"mcpServers": {
"ragdoll-mcp-server": {
"command": "npx",
"args": ["-y", "ragdoll-mcp-server"],
"env": {
"RAGDOLL_API_KEY": "your-ragdoll-api-key",
"RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
}
}
}
}
Alternatively, you can run the server locally:
{
"mcpServers": {
"ragdoll-mcp-server": {
"command": "bun",
"args": ["run", "/path/to/mcp-ragdoll-server/index.ts"],
"env": {
"RAGDOLL_API_KEY": "your-ragdoll-api-key",
"RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
}
}
}
}
Windsurf
To install the Ragdoll MCP server in Windsurf IDE:
Create or edit your mcp_config.json file with the following configuration:
{
"mcpServers": {
"ragdoll-mcp-server": {
"command": "npx",
"args": ["-y", "ragdoll-mcp-server"],
"env": {
"RAGDOLL_API_KEY": "your-ragdoll-api-key",
"RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
}
}
}
}
Cline
To install the Ragdoll MCP server in Cline:
Create or edit your cline_mcp_settings.json file with the following configuration:
{
"mcpServers": {
"ragdoll-mcp-server": {
"command": "npx",
"args": ["-y", "ragdoll-mcp-server"],
"env": {
"RAGDOLL_API_KEY": "your-ragdoll-api-key",
"RAGDOLL_KNOWLEDGE_BASE_ID": "your-knowledge-base-id"
}
}
}
}
Usage
Once connected, you can query your Ragdoll knowledge base with the following parameters:
query(string, required): The search query to find relevant informationtopK(number, optional): Number of results to return (1-10)rerank(boolean, optional): Whether to rerank results
Example usage in your LLM client:
You can ask questions about your knowledge base content.
Development
This project uses the Model Context Protocol SDK. For more information, refer to the MCP documentation.
Support
For issues or questions about this MCP server, please submit an issue on GitHub.
